Adapting sample size in particle filters through KLD-resampling

TL;DR

This paper introduces an adaptive resampling method for particle filters that adjusts the number of particles based on the Kullback-Leibler distance to better match the true posterior distribution, improving efficiency.

Contribution

It presents a novel KLD-based resampling approach that accounts for distribution mismatch, enhancing particle filter performance over existing methods.

Findings

Demonstrated improved efficiency in target tracking simulations.

Compared favorably to Fox's KLD-sampling in accuracy and flexibility.

Validated the method's theoretical rigor and practical benefits.

Abstract

This letter provides an adaptive resampling method. It determines the number of particles to resample so that the Kullback-Leibler distance (KLD) between distribution of particles before resampling and after resampling does not exceed a pre-specified error bound. The basis of the method is the same as Fox's KLD-sampling but implemented differently. The KLD-sampling assumes that samples are coming from the true posterior distribution and ignores any mismatch between the true and the proposal distribution. In contrast, we incorporate the KLD measure into the resampling in which the distribution of interest is just the posterior distribution. That is to say, for sample size adjustment, it is more theoretically rigorous and practically flexible to measure the fit of the distribution represented by weighted particles based on KLD during resampling than in sampling. Simulations of target tracking demonstrate the efficiency of our method.